| Dimension | Shared | Only in A | Only in B | Overlap |
|---|---|---|---|---|
| Sections | 0 | 1 | 5 | 0% |
| Commands | 0 | 0 | 0 | — |
| Section tags | 0 | 0 | 1 | 0% |
What each file covers
Sections
0 shared · 1 only in A · 5 only in B- − CareerSwarm
- + Agent Prompts
- + Tailor
- + Profiler
- + Scribe
- + Roast
Commands
neither file has anySection tags
0 shared · 0 only in A · 1 only in B- + agent-behaviour
Line diff
zganich/careerswarm-honeycomb · .cursorrules
@@ −1 @@
1# CareerSwarm
2
3AI-powered career evidence platform: Master Profile, achievements (STAR), 7-stage agent pipeline (Scout → Qualifier → Profiler → Tailor → Scribe → Assembler → Success Predictor), Resume Roast, application tracker.
4
5**Full rules:** See `.cursor/rules/` for core, architecture, agent-prompts, flywheel, pivot, roast.
6
7**Reference:** [CONTEXT_FOR_NEW_CHAT.md](CONTEXT_FOR_NEW_CHAT.md) for handoff and detailed context.
8
zganich/careerswarm-honeycomb · .cursor/rules/agent-prompts.mdc
@@ +1 @@
1---
2description: Agent prompt standards for Tailor, Profiler, Scribe, Roast
3globs: server/agents/*.ts,server/roast.ts
4alwaysApply: false
5---
6
7# Agent Prompts
8
9## Tailor
10
11- Job persona (Federal, Tech, Creative, Healthcare, Skilled Trades, Corporate, Academic, Legal, Education/Nonprofit) and format (A/B/C) are **inferred from the JD only**; Tailor does not receive a pre-set industry or format. Page length is inferred from work history (career level) and industry rules.
12- Use CAR framework (Context → Action → Result); for Tech & Engineering the prompt also specifies Google XYZ formula.
13- Quantify ALL results (%, $, numbers)
14- FORBIDDEN: orchestrated, spearheaded, visionary, synergy, leverage, utilize, facilitate, champion, holistic, paradigm, robust
15- Output: Markdown only
16
17## Profiler
18
19- Output: JSON `{pain_points: [], strategic_hook: ''}`
20- Focus: Churn, Expansion, Technical Debt
21
22## Scribe
23
24- LinkedIn: 300 char max
25- Email: 150 word max
26- NO coffee chat requests
27- Ask strategic questions only
28
29## Roast
30
31- 0-100 score + 3 "Million-Dollar Mistakes"
32- Brutal honesty, no AI fluff
33
@@ −1 +1 @@
1−# CareerSwarm
1+---
2+description: Agent prompt standards for Tailor, Profiler, Scribe, Roast
3+globs: server/agents/*.ts,server/roast.ts
4+alwaysApply: false
5+---
26
3−AI-powered career evidence platform: Master Profile, achievements (STAR), 7-stage agent pipeline (Scout → Qualifier → Profiler → Tailor → Scribe → Assembler → Success Predictor), Resume Roast, application tracker.
7+# Agent Prompts
48
5−**Full rules:** See `.cursor/rules/` for core, architecture, agent-prompts, flywheel, pivot, roast.
9+## Tailor
610
7−**Reference:** [CONTEXT_FOR_NEW_CHAT.md](CONTEXT_FOR_NEW_CHAT.md) for handoff and detailed context.
11+- Job persona (Federal, Tech, Creative, Healthcare, Skilled Trades, Corporate, Academic, Legal, Education/Nonprofit) and format (A/B/C) are **inferred from the JD only**; Tailor does not receive a pre-set industry or format. Page length is inferred from work history (career level) and industry rules.
12+- Use CAR framework (Context → Action → Result); for Tech & Engineering the prompt also specifies Google XYZ formula.
13+- Quantify ALL results (%, $, numbers)
14+- FORBIDDEN: orchestrated, spearheaded, visionary, synergy, leverage, utilize, facilitate, champion, holistic, paradigm, robust
15+- Output: Markdown only
16+
17+## Profiler
18+
19+- Output: JSON `{pain_points: [], strategic_hook: ''}`
20+- Focus: Churn, Expansion, Technical Debt
21+
22+## Scribe
23+
24+- LinkedIn: 300 char max
25+- Email: 150 word max
26+- NO coffee chat requests
27+- Ask strategic questions only
28+
29+## Roast
30+
31+- 0-100 score + 3 "Million-Dollar Mistakes"
32+- Brutal honesty, no AI fluff
833
